An Innovative Machine Learning Based Multistage Signal Amplification Method Breaks through the Detection Limits of Conventional Optical Sensors.

Journal: ACS sensors
Published Date: Jul 30, 2025

Abstract

Surface plasmon resonance (SPR) enables in situ, label-free, real-time molecular detection. However, traditional SPR biosensors require complex and precise large-scale equipment, with detection limits constrained by multiple factors, complicating and prolonging biosensor development, especially in emergencies. To address these challenges, we introduce an innovative multistage signal amplification metasurface plasmon resonance (MSA-MetaSPR) method based on a complete inverse design. Adherent to the principle of signal maximization, we divided the system into three main components: the sensor, the capturer, and the signal acquisition unit. By introducing an optical density (OD)-based inverse design method, we designed a MetaSPR chip with a sensitivity of up to 573 nm/RIU and developed artificial antibodies with a 3-fold increase in affinity. Finally, we introduced a novel analytical method for processing biosensor data. This complete inverse design-based multistage amplification method achieves a nearly 1200-fold improvement compared to undesign-based sensors and an almost 150-fold improvement over conventional SPR methods. This proposed approach accelerates the development of biosensors for urgent situations and significantly advances the capabilities of SPR sensor technologies.

Authors

  • Yihui Yang
    Department of Anesthesiology, Third Affiliated Hospital of Zunyi Medical University, Guizhou Province, China.
  • Jiawei Liang
    Department of Nano Biosensing and Artificial Intelligence, College of Life Science and Technology, State Key Laboratory for Diagnosis and Treatment of Severe Zoonotic Infectious Diseases, Huazhong University of Science and Technology, Wuhan 430074, China.
  • Hongli Fan
    Department of Biomedical Engineering, Johns Hopkins School of Medicine, Baltimore, Maryland, USA.
  • Yu Qin
    School of Information and Electronics, Beijing Institute of Technology, 5 Zhongguancun South Street, Beijing, China.
  • Mingqian Chen
    Department of Nano Biosensing and Artificial Intelligence, College of Life Science and Technology, State Key Laboratory for Diagnosis and Treatment of Severe Zoonotic Infectious Diseases, Huazhong University of Science and Technology, Wuhan 430074, China.
  • Wen Li
  • Zifang Song
    Department of Hepatobiliary Surgery, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei 430022, China.
  • Gang Logan Liu
    Department of Nano Biosensing and Artificial Intelligence, College of Life Science and Technology, State Key Laboratory for Diagnosis and Treatment of Severe Zoonotic Infectious Diseases, Huazhong University of Science and Technology, Wuhan 430074, China.
  • Wenjun Hu
    School of Information and Engineering, Huzhou Teachers College, Huzhou 313000, China.

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals